fuente: https://cybersecuritynews.com/plugin4shell-zero-click-rce/
Plugin4Shell is a high-severity, zero-click remote code execution vulnerability affecting major AI coding agents, including Anthropic Claude Code, OpenAI Codex, GitHub Copilot, and Google Gemini CLI.
The flaw allows a malicious plugin update to execute attacker-controlled code without requiring a user to click, approve, or reinstall anything.
Plugin4Shell targets the software supply chain behind AI agents rather than the AI models themselves. Modern coding agents can install plugins, skills, and extensions from community marketplaces.
These add-ons often inherit the same permissions as the developer running the agent, including access to local source code, cloud credentials, SSH keys, internal repositories, production systems, and secrets.
The issue lies in the way affected agents handle SHA-pinned plugin versions. Marketplace systems commonly pin a plugin to a specific Git commit hash after it has been reviewed. This is intended to ensure the agent installs the exact approved code rather than a newer or modified version.
El 12 de agosto de 2026, Phoenix Contact reveló tres vulnerabilidades en el firmware de PLCnext. Una de ellas, CVE-2025-41771, permite que un atacante con pocos...
Leer artículo →Una nueva técnica de ataque manipula el controlador de memoria de un ordenador para eludir algunas de las medidas de seguridad de hardware más robustas integrad...
Leer artículo →La petrolera Shell ha confirmado que está investigando un posible incidente de seguridad después de que el grupo de ransomware Clop afirmara haber robado 89 GB...
Leer artículo →